Files and memory at 8K context
| Quant | File | Files | + KV + runtime | Smallest fit | Source |
|---|---|---|---|---|---|
| Q4_K_M openbmb/MiniCPM5-1B-GGUF | 0.64 GiB | 1 | 1.8 GiB | 8 GB GPU | HF files |
| Q5_K_M Abiray/MiniCPM5-1B-GGUF | 0.73 GiB | 1 | 1.9 GiB | 8 GB GPU | HF files |
| Q8_0 openbmb/MiniCPM5-1B-GGUF | 1.07 GiB | 1 | 2.3 GiB | 8 GB GPU | HF files |
| FP16 openbmb/MiniCPM5-1B-GGUF | 2.02 GiB | 1 | 3.2 GiB | 8 GB GPU | HF files |
| MLX 4-bit openbmb/MiniCPM5-1B-MLX | 0.57 GiB | 1 | 1.8 GiB | 8 GB Mac | HF files |
| MLX 8-bit mlx-community/MiniCPM5-1B-8bit | 1.07 GiB | 1 | 2.3 GiB | 8 GB Mac | HF files |
Sizes are exact file bytes (text weights; projectors listed separately). “+” = recurrent state or other terms unknown. Smallest fit adds 0.5 GiB spare; Macs use 75% of memory.
Quality
Artificial Analysis Intelligence Index
8.8 AA estimate
Variant: MiniCPM5-1B (Reasoning) · observed 2026-10-17 · source
Rank #67 of 75 researched 2026 models.
Arena text rating
Unknown
Scores describe the evaluated hosted variant, not each quantized file. AA and Arena are never averaged.
Reported speeds 0
No reported measurement yet. Submit one.
Community threads
- Interpretation tools: SAE weights (english only) brain atlas SQLite database Hugging Face · 2026-07-26
- Any plan to support ltertlm? Hugging Face · 2026-06-01
Qualitative signals only; titles are not verified claims.